Active learning of affordances for robot use of household objects

Chang Wang, Koen V. Hindriks, Robert Babuska

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

Abstract

Learning to perform household tasks is a key step towards developing cognitive service robots. This requires that robots are capable of discovering how to use human-designed products. In this paper, we propose an active learning approach for acquiring object affordances and manipulation skills in a bottom-up manner. We address affordance learning in continuous state and action spaces without manual discretization of states or exploratory motor primitives. During exploration in the action space, the robot learns a forward model to predict action effects. It simultaneously updates the active exploration policy through reinforcement learning, whereby the prediction error serves as the intrinsic reward. By using the learned forward model, motor skills are obtained to achieve goal states of an object. We demonstrate through real-world experiments that a humanoid robot NAO is able to autonomously learn how to manipulate two types of garbage cans with lids that need to be opened and closed by different motor skills.

Original languageEnglish
Title of host publication2014 IEEE-RAS International Conference on Humanoid Robots, Humanoids 2014
PublisherACM, IEEE Computer Society
Pages566-572
Number of pages7
Volume2015-February
ISBN (Electronic)9781479971749
DOIs
Publication statusPublished - 1 Jan 2015
Externally publishedYes
Event2014 14th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2014 - Madrid, Spain
Duration: 18 Nov 201420 Nov 2014

Conference

Conference2014 14th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2014
CountrySpain
CityMadrid
Period18/11/1420/11/14

Fingerprint Dive into the research topics of 'Active learning of affordances for robot use of household objects'. Together they form a unique fingerprint.

Cite this